Mark
/
celeste-ai
Archived
1
0
Fork 0
This repository has been archived on 2023-11-28. You can view files and clone it, but cannot push or open issues/pull-requests.
celeste-ai/celeste
Mark 2ff526a072
Changed hyperparameters, actions, action selection, and reward system
2023-02-24 14:16:43 -08:00
..
celeste_ai Changed hyperparameters, actions, action selection, and reward system 2023-02-24 14:16:43 -08:00
resources Added stage 1 images 2023-02-18 18:50:22 -08:00
README.md Reorganized celeste code 2023-02-19 20:57:19 -08:00
ffmpeg.sh Improved ffmpeg script 2023-02-24 14:11:56 -08:00
plot.py Added new plotting script 2023-02-19 20:57:32 -08:00
pyproject.toml Reorganized celeste code 2023-02-19 20:57:19 -08:00

README.md

Celeste-AI: A Celeste Classic DQL Agent

This is an attempt to create an agent that learns to play Celeste Classic.

Contents

  • ./resources: contain files these scripts require. Notably, we have an (old) version of PICO-8 that's known to work with this script, and a version of Celeste Classic with telementery and delays called hackcel.p8.

Setup

This is designed to work on Linux. You will need xdotool to send keypresses to the game.

  1. cd into this directory
  2. Make and enter a venv
  3. pip install -e .